Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1491 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1385985 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1645589 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1441. Min Act: -0.0001

Data Index: 379044 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1405. Min Act: -0.0001

Data Index: 381211 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1375. Min Act: -0.0001

Data Index: 402273 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1128. Min Act: -0.0001

Data Index: 489383 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1562291 (Python Code)

Max Activating Token Index: 198

Text #7

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1177. Min Act: -0.0001

Data Index: 112053 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1232. Min Act: -0.0001

Data Index: 671582 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1223. Min Act: -0.0001

Data Index: 905203 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1135. Min Act: -0.0001

Data Index: 520836 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1276. Min Act: -0.0001

Data Index: 823982 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1130. Min Act: -0.0001

Data Index: 380387 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1241. Min Act: -0.0001

Data Index: 584217 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1613603 (Python Code)

Max Activating Token Index: 288

Text #15

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1199. Min Act: -0.0001

Data Index: 940672 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1207. Min Act: -0.0001

Data Index: 280088 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1131. Min Act: -0.0001

Data Index: 4615 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1178330 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1508727 (Python Code)

Max Activating Token Index: 1014